Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ggerganov, Romanov, Kasparov

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вля
    0.44
    Კ
    0.42
    工地
    0.40
    াবার
    0.39
    িনি
    0.39
    DEFGHI
    0.39
     Vaughan
    0.38
    agis
    0.38
     Bürgermeister
    0.38
    ائیگی
    0.38
    POSITIVE LOGITS
    ov
    1.48
    OV
    1.23
    ova
    1.12
    мов
    1.02
    atov
    1.02
    тов
    1.01
    arov
    1.00
    нов
    0.99
    дов
    0.97
    anov
    0.96
    Act Density 0.008%

    No Known Activations